Skip to content

Beta: real launches, updated every morning. Rankings may change while we tune them.

TheoremSmith

Making models better at formal verification will help push the boundaries of math research and significantly reduce the number of bugs in our code.

118Rank on 11 November 2026New on 11 Nov

TheoremSmith launched on 10 November 2026. It ranked #118 on Daily Launch on 11 November 2026 with a Launch Score of 10, from 10 points on Show HN. It was new in the ranking that day.

Visit site#7 on Show HN the day before · 10 points
Share

What is TheoremSmith?

Making models better at formal verification will help push the boundaries of math research and significantly reduce the number of bugs in our code. Recently, training models on RL environments (tasks paired with verifiers that reward correct solutions) has driven big gains in model performance, and proofs are unusually easy to verify. Here we introduce TheoremSmith, a pipeline for generating synthetic formal verification environments. It reliably creates multi-hour, frontier-difficulty tasks and can scale throughput effectively.

From its Hacker News post

TheoremSmith is a launch on Show HN.

Daily Launch card for TheoremSmith

In its own words

Mass-Producing Hard Proof Problems to Train LLMs

From its Show HN post

Launch timeline

  1. Show HNPosted on Show HN

  2. Show HN10 points, ranked #160 on Daily Launch

Launch Score, last 7 days

Ranked on one day so far: 10 of 100 on 11 November.

Similar new launches